Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/psd401/psd-claude-plugins/claude-mdgit clone --depth 1 https://github.com/psd401/psd-claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/psd401/psd-claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/psd401/psd-claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/psd401/psd-claude-plugins/claude-md.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.04387 | $0.04387 |
| Opus 5 | $0.02194 | $0.02194 |
| Sonnet 5 | $0.00877 | $0.00877 |
| Haiku 4.5 | $0.00439 | $0.00439 |
Grade A, and why
psd-claude-plugins CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Repository Overview
This is the PSD Plugin Marketplace — a multi-plugin marketplace for Claude Code and Claude Cowork, maintained by Peninsula School District.
Version: 2.28.4 Status: Production-Ready
Plugins
| Plugin | Purpose | Skills | Agents |
|---|---|---|---|
psd-coding-system |
AI-assisted development workflows | 9 | 44 |
psd-productivity |
Productivity workflows (Cowork-friendly) | 38 | 1 |
Architecture
Multi-Plugin Marketplace Structure
psd-claude-plugins/
.claude-plugin/marketplace.json # lists both plugins — see CRITICAL RULES below
plugins/
psd-coding-system/ # skills/ (9), agents/ (44 in 8 category dirs), hooks/, scripts/, workflows/, docs/patterns/
psd-productivity/ # skills/ (38), agents/ (enrollment-validator)
docs/learnings/ # canonical learnings location (see Learning Data below)
Explore with ls — the tree is not duplicated here.
Plugin Independence
- Plugins cannot declare dependencies on each other
- Skills cannot invoke other skills — workflows chain via Task tool delegation
- Each plugin ships its own agents
enabledPluginsin.claude/settings.jsonallows selective enabling/disabling
psd-coding-system Skills (9 total)
v3.0.0 consolidated 21 overlapping skills into 3 disciplined surfaces + utilities. "Done" is a machine-checkable Definition of Done (docs/patterns/definition-of-done.md), enforced by a verify gate + Stop hook, not agent goodwill.
| Skill | Description |
|---|---|
/plan |
Clarify → research (parallel) → design → emit tasks + a machine-checkable Definition of Done (+ contract-compliant issues). Absorbs architect/brainstorm/scope/product-manager/deepen-plan/issue |
/lfg |
Autonomous build-to-done: implement → verify the full DoD (build/lint-zero-warning/typecheck/full suite/Playwright + screenshots) → open PR with visual evidence → watch CI + the project's AI reviewers and fix every round until 100% clean. Absorbs work/test/debug/optimize/review-pr/security-audit |
/evolve |
Compound learnings into CLAUDE.md/patterns/agents then prune them; release tracking; competitor compare |
/setup |
Write .psd/verify.json — the per-project verification gate (commands, E2E flows, strictness, AI-reviewer logins, commit-learnings, active review agents) |
/worktree |
Git worktree management + multi-window parallel how-to + clean post-merge hygiene (prune worktrees, delete merged local/remote branches, close orphaned issues — restores /clean-branch) |
/bump-version |
Version bump ritual (absorbs /changelog) — three independent tracks |
/psd-sign |
Sign, notarize, and package a macOS .app into a .pkg for PSD Jamf Self Service — full Apple Developer ID pipeline (salvaged from PR #39 in v3.4.0) |
/chad-review |
Strip the showing-off from an artifact (docs, prose, skills, landing pages) — Chad ↔ defender review loop on a clone, N rounds, unresolved tensions to the human. Vendored from nityeshaga/claude-code-essentials (v0.5.0, no upstream license) in v3.6.0. Workflow-tool path is agent-expensive — see the PSD notes in its SKILL.md |
/hallmark |
Anti-AI-slop visual design surface — picks a macrostructure for the brief, dresses it in one of 21 OKLCH themes, runs 57 slop-test gates + a pre-emit self-critique. Four verbs: default (design) · audit (score, no edits) · redesign (keep copy/IA/brand, rebuild the visual layer) · study (extract a design's DNA from a screenshot/URL, never pixel-clones). Vendored from nutlope/hallmark (v1.1.0, MIT — LICENSE.upstream travels with it) in v3.7.0. Styles; does not ship — /lfg still owns the verify gate. Upstream site/css/tokens.css is vendored to references/tokens.css because 16 of the 21 themes live only there |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed 0c97d3ef056b
- 4d ago First seen · 258 lines · 4,387 tokens per session scan A bed9762e5ae6
psd-claude-plugins CLAUDE.md is an instructions file published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 3d ago), licensed MIT. It adds 4,387 tokens to every session, about $0.0219 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.